Discovering fair representations in the data domain
- Submitting institution
-
University of Sussex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 335583_83076
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR.2019.00842
- Title of conference / published proceedings
- Conference on Computer Vision and Pattern Recognition (CVPR)
- First page
- 8219
- Volume
- 1
- Issue
- -
- ISSN
- 2575-7075
- Open access status
- Compliant
- Month of publication
- June
- Year of publication
- 2019
- URL
-
https://doi.ieeecomputersociety.org/10.1109/CVPR.2019.00842
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- "This paper was the first to advocate interpretability/transparency in algorithmic fairness. We specifically focussed on enforcing fairness in representation learning. Thanks to this work, Quadrianto obtained an ERC Starting Grant [1] to develop models and algorithms for fairness and transparency, has been invited to be an ELLIS (European Laboratory for Learning and Intelligent Systems) Scholar for the Human-Centric Machine Learning programme [2], and to set up a new BCAM (Basque Center for Applied Mathematics) Severo Ochoa Strategic Lab on Trustworthy Machine Learning in Spain (Contact: Prof. Lozano, jlozano@bcamath.org, Scientific Director of BCAM).
[1] BayesianGDPR, 1.4M€, https://cordis.europa.eu/project/id/851538
[2] https://ellis.eu/programs/human-centric-machine-learning"
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -